Training in progress, step 60000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68a8797cd76a94ad3c6a56a7adc2bc1ac7c0398bdd3f9b8fd64c36634fe35a09
+oid sha256:37c3e862658b65ca1c890f9f0b04bb5662ecbde856aff6689ee9869db46d9afb
 size 242247040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97396477b00599023e8b9271f179e4f9045180aadb813660ee60fd378f08ad79
+oid sha256:bb4f4c4c584d8852a4f54227a4581f8060bac83c9d018fe6714f1e4cfab0c599
 size 484395467

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea14e437e9bde41dd138cf43e193fe8b9138dbdf51219ee5b3285011252c1d78
+oid sha256:45f40ff98c14fbbe6809e0534caa0e9d45b0cb19d01a65ef2e74b4fd68c0c624
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f695b69ce20f0a3ab929251148b7f644620cd816442ed26ba4e618a194a3b03
+oid sha256:72db15717b2d4617f35951f97b2fabd7d047d3b7fe2b49b17504acc7cc4ec68d
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51d2908fdfd796e12d1265cbd5e8f7336ad5dbe4ebdb91a07beab91214e64999
+oid sha256:b62892e5bace3013f6f9fb7a156e9e583088be1e4d87080b99784c2eb93c454b
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 55000,
-  "best_metric": 25.42,
-  "best_model_checkpoint": "/content/en_kin_model/checkpoint-55000",
-  "epoch": 12.999290947766486,
+  "best_global_step": 60000,
+  "best_metric": 25.69,
+  "best_model_checkpoint": "/content/en_kin_model/checkpoint-60000",
+  "epoch": 14.181044670290712,
   "eval_steps": 5000,
-  "global_step": 55000,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -877,6 +877,85 @@
       "eval_samples_per_second": 138.762,
       "eval_steps_per_second": 1.105,
       "step": 55000
+    },
+    {
+      "epoch": 13.117466320018908,
+      "grad_norm": 0.72737056016922,
+      "learning_rate": 0.0003615810122196134,
+      "loss": 2.507847412109375,
+      "step": 55500
+    },
+    {
+      "epoch": 13.235641692271331,
+      "grad_norm": 0.7681657075881958,
+      "learning_rate": 0.00035916764747355705,
+      "loss": 2.53956298828125,
+      "step": 56000
+    },
+    {
+      "epoch": 13.353817064523753,
+      "grad_norm": 0.8309329748153687,
+      "learning_rate": 0.0003567416463147021,
+      "loss": 2.55163134765625,
+      "step": 56500
+    },
+    {
+      "epoch": 13.471992436776176,
+      "grad_norm": 0.7395633459091187,
+      "learning_rate": 0.0003543032895584072,
+      "loss": 2.56509521484375,
+      "step": 57000
+    },
+    {
+      "epoch": 13.590167809028598,
+      "grad_norm": 0.7688890099525452,
+      "learning_rate": 0.0003518528594502208,
+      "loss": 2.564052734375,
+      "step": 57500
+    },
+    {
+      "epoch": 13.708343181281021,
+      "grad_norm": 0.7620258331298828,
+      "learning_rate": 0.00034939063963321005,
+      "loss": 2.583301513671875,
+      "step": 58000
+    },
+    {
+      "epoch": 13.826518553533443,
+      "grad_norm": 0.7235142588615417,
+      "learning_rate": 0.0003469169151151291,
+      "loss": 2.5848076171875,
+      "step": 58500
+    },
+    {
+      "epoch": 13.944693925785867,
+      "grad_norm": 0.7277477979660034,
+      "learning_rate": 0.00034443197223542793,
+      "loss": 2.59660107421875,
+      "step": 59000
+    },
+    {
+      "epoch": 14.062869298038288,
+      "grad_norm": 0.6620763540267944,
+      "learning_rate": 0.0003419360986321088,
+      "loss": 2.519939697265625,
+      "step": 59500
+    },
+    {
+      "epoch": 14.181044670290712,
+      "grad_norm": 0.7132055163383484,
+      "learning_rate": 0.0003394295832084308,
+      "loss": 2.478825439453125,
+      "step": 60000
+    },
+    {
+      "epoch": 14.181044670290712,
+      "eval_bleu": 25.69,
+      "eval_loss": 2.8314549922943115,
+      "eval_runtime": 39.5905,
+      "eval_samples_per_second": 139.554,
+      "eval_steps_per_second": 1.111,
+      "step": 60000
     }
   ],
   "logging_steps": 500,
@@ -905,7 +984,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9997212897876378e+17,
+  "total_flos": 2.1813850903648666e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null